Newest papers

CLOSER: Evidence-Aware Active Visual Verification for Embodied Object-Goal Navigation

Pengying Wu, Mingye Jiang, Yunze Hu, Zhejia Wen, Kangjie Zhou, Zongru Yang, Zhe Peng, Chang Liu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28476 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

O agente geralmente se baseia em um detector de objetos, mas deve julgar on-line a partir de um fluxo de vídeo egocêntrico limitado, às vezes um único quadro, se um candidato detectado é o alvo. Os detectores muitas vezes confiavelmente confundem objetos semelhantes, como um sofá para uma cama, e parando em um falso positivo falha o episódio. Os sistemas predominantes também abordam os candidatos com ganância, deixando-os ocultos ou parcialmente observados. Nós apresentamos CLOSER, um framework de verificação ativo consciente de evidências que trata a parada como a aquisição de evidências de circuito fechado, combinando a verificação do modelo de linguagem de visão (VLM) com a percepção ativa. Os sistemas CLOSER-tune-tune

Machine translation (Meta M2M100); the English original follows.

Abstract

Object-goal navigation (ObjectNav) requires an embodied agent to find an instance of a specified category in an unseen environment and stop near it. The agent typically relies on an object detector but must judge online from a limited egocentric video stream, sometimes a single frame, whether a detected candidate is the target. Detectors often confidently mistake similar objects, such as a sofa for a bed, and stopping at a false positive fails the episode. Prevailing systems also approach candidates greedily, leaving them occluded or partially observed. We present CLOSER, an evidence-aware active verification framework that treats stopping as closed-loop evidence acquisition, coupling vision-language model (VLM) verification with active perception. CLOSER fine-tunes an open-source VLM to label each view of a candidate tracked across frames as target, non-target, or uncertain, selects complementary views with an embedding-based diversity gate, and fuses their per-view probabilities with a lightweight network. If the fused judgment remains uncertain, a diffusion policy drives the agent toward the candidate using only the tracked mask and depth until the decision becomes decisive. CLOSER runs locally and plugs into existing ObjectNav systems without retraining them. On Gibson and Habitat-Matterport 3D, it raises average success rate by 3.6 points and success weighted by path length by 2.0 points, showing that verifying evidence before committing improves embodied navigation.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Embodied cognition, Mistake, Artificial intelligence, Computer vision, Object (grammar)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange